agora inbox for pgsql-hackers@postgresql.org  
help / color / mirror / Atom feed
[PATCH v28 01/11] Add a syntax to create Incrementally Maintainable Materialized Views
1528+ messages / 2 participants
[nested] [flat]

* [PATCH v28 01/11] Add a syntax to create Incrementally Maintainable Materialized Views
@ 2019-12-20 01:05 Yugo Nagata <nagata@sraoss.co.jp>
  0 siblings, 0 replies; 1528+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:05 UTC (permalink / raw)

Allow to create Incrementally Maintainable Materialized View (IMMV)
by using INCREMENTAL option in CREATE MATERIALIZED VIEW command
as follow:

     CREATE [INCREMANTAL] MATERIALIZED VIEW xxxxx AS SELECT ....;
---
 src/backend/parser/gram.y     | 32 +++++++++++++++++++++-----------
 src/include/nodes/primnodes.h |  1 +
 src/include/parser/kwlist.h   |  1 +
 3 files changed, 23 insertions(+), 11 deletions(-)

diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index 39ab7eac0d..3534b37f81 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -465,6 +465,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 
 %type <range>	OptTempTableName
 %type <into>	into_clause create_as_target create_mv_target
+%type <boolean>	incremental
 
 %type <defelt>	createfunc_opt_item common_func_opt_item dostmt_opt_item
 %type <fun_param> func_arg func_arg_with_default table_func_column aggr_arg
@@ -721,7 +722,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	HANDLER HAVING HEADER_P HOLD HOUR_P
 
 	IDENTITY_P IF_P ILIKE IMMEDIATE IMMUTABLE IMPLICIT_P IMPORT_P IN_P INCLUDE
-	INCLUDING INCREMENT INDENT INDEX INDEXES INHERIT INHERITS INITIALLY INLINE_P
+	INCLUDING INCREMENT INCREMENTAL INDENT INDEX INDEXES INHERIT INHERITS INITIALLY INLINE_P
 	INNER_P INOUT INPUT_P INSENSITIVE INSERT INSTEAD INT_P INTEGER
 	INTERSECT INTERVAL INTO INVOKER IS ISNULL ISOLATION
 
@@ -4637,32 +4638,34 @@ opt_with_data:
  *****************************************************************************/
 
 CreateMatViewStmt:
-		CREATE OptNoLog MATERIALIZED VIEW create_mv_target AS SelectStmt opt_with_data
+		CREATE OptNoLog incremental MATERIALIZED VIEW create_mv_target AS SelectStmt opt_with_data
 				{
 					CreateTableAsStmt *ctas = makeNode(CreateTableAsStmt);
 
-					ctas->query = $7;
-					ctas->into = $5;
+					ctas->query = $8;
+					ctas->into = $6;
 					ctas->objtype = OBJECT_MATVIEW;
 					ctas->is_select_into = false;
 					ctas->if_not_exists = false;
 					/* cram additional flags into the IntoClause */
-					$5->rel->relpersistence = $2;
-					$5->skipData = !($8);
+					$6->rel->relpersistence = $2;
+					$6->skipData = !($9);
+					$6->ivm = $3;
 					$$ = (Node *) ctas;
 				}
-		| CREATE OptNoLog MATERIALIZED VIEW IF_P NOT EXISTS create_mv_target AS SelectStmt opt_with_data
+		| CREATE OptNoLog incremental MATERIALIZED VIEW IF_P NOT EXISTS create_mv_target AS SelectStmt opt_with_data
 				{
 					CreateTableAsStmt *ctas = makeNode(CreateTableAsStmt);
 
-					ctas->query = $10;
-					ctas->into = $8;
+					ctas->query = $11;
+					ctas->into = $9;
 					ctas->objtype = OBJECT_MATVIEW;
 					ctas->is_select_into = false;
 					ctas->if_not_exists = true;
 					/* cram additional flags into the IntoClause */
-					$8->rel->relpersistence = $2;
-					$8->skipData = !($11);
+					$9->rel->relpersistence = $2;
+					$9->skipData = !($12);
+					$9->ivm = $3;
 					$$ = (Node *) ctas;
 				}
 		;
@@ -4679,9 +4682,14 @@ create_mv_target:
 					$$->tableSpaceName = $5;
 					$$->viewQuery = NULL;		/* filled at analysis time */
 					$$->skipData = false;		/* might get changed later */
+					$$->ivm = false;
 				}
 		;
 
+incremental:	INCREMENTAL				{ $$ = true; }
+				| /*EMPTY*/				{ $$ = false; }
+		;
+
 OptNoLog:	UNLOGGED					{ $$ = RELPERSISTENCE_UNLOGGED; }
 			| /*EMPTY*/					{ $$ = RELPERSISTENCE_PERMANENT; }
 		;
@@ -17055,6 +17063,7 @@ unreserved_keyword:
 			| INCLUDE
 			| INCLUDING
 			| INCREMENT
+			| INCREMENTAL
 			| INDENT
 			| INDEX
 			| INDEXES
@@ -17621,6 +17630,7 @@ bare_label_keyword:
 			| INCLUDE
 			| INCLUDING
 			| INCREMENT
+			| INCREMENTAL
 			| INDENT
 			| INDEX
 			| INDEXES
diff --git a/src/include/nodes/primnodes.h b/src/include/nodes/primnodes.h
index 792a743f72..e87a105707 100644
--- a/src/include/nodes/primnodes.h
+++ b/src/include/nodes/primnodes.h
@@ -146,6 +146,7 @@ typedef struct IntoClause
 	/* materialized view's SELECT query */
 	Node	   *viewQuery pg_node_attr(query_jumble_ignore);
 	bool		skipData;		/* true for WITH NO DATA */
+	bool		ivm;			/* true for WITH IVM */
 } IntoClause;
 
 
diff --git a/src/include/parser/kwlist.h b/src/include/parser/kwlist.h
index f5b2e61ca5..a3fbfedbf4 100644
--- a/src/include/parser/kwlist.h
+++ b/src/include/parser/kwlist.h
@@ -207,6 +207,7 @@ PG_KEYWORD("in", IN_P, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("include", INCLUDE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("including", INCLUDING, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("increment", INCREMENT, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("incremental", INCREMENTAL, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("indent", INDENT, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("index", INDEX, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("indexes", INDEXES, UNRESERVED_KEYWORD, BARE_LABEL)
-- 
2.25.1


--Multipart=_Thu__1_Jun_2023_23_59_09_+0900_/G5+8nG46.f1T42K
Content-Type: text/x-diff;
 name="v28-0002-Add-relisivm-column-to-pg_class-system-catalog.patch"
Content-Disposition: attachment;
 filename="v28-0002-Add-relisivm-column-to-pg_class-system-catalog.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription
@ 2026-07-03 14:03 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:03 UTC (permalink / raw)

Following the approach of RangeVarGetRelidExtended() for relations, add a
retry loop that includes name resolution, ownership check, and lock
acquisition in AlterSubscription() and DropSubscription().

The loop records SharedInvalidMessageCounter, resolves the subscription name
to an OID, checks ownership, then locks the subscription. If the invalidation
counter changed (indicating concurrent DDL), we save the current OID and
retry. On the next iteration, if the name still resolves to the same OID,
we're done (already holding the correct lock). If it resolves to a different
OID, we release the old lock and acquire the new one.

This mirrors RangeVarGetRelidExtended()'s behavior: the lock is kept across
retries to avoid a window where another session could have committed concurrent
DDL modifying the ownership and/or the name resolution.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/subscriptioncmds.c | 167 +++++++++++++++++-------
 1 file changed, 118 insertions(+), 49 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e23b366a87d..866341c2cfb 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -50,6 +50,7 @@
 #include "replication/walsender.h"
 #include "replication/worker_internal.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -1592,23 +1593,67 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 
 	rel = table_open(SubscriptionRelationId, RowExclusiveLock);
 
-	/* Fetch the existing tuple. */
-	tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME, ObjectIdGetDatum(MyDatabaseId),
-							  CStringGetDatum(stmt->subname));
+	/*
+	 * Lock the subscription so nobody else can do anything with it.
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
+	 */
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-	subid = form->oid;
+			tup = SearchSysCacheCopy2(SUBSCRIPTIONNAME,
+									  ObjectIdGetDatum(MyDatabaseId),
+									  CStringGetDatum(stmt->subname));
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer. So we're done. If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			heap_freetuple(tup);
+		}
+	}
 
 	/* parse and check options */
 	switch (stmt->kind)
@@ -1686,25 +1731,6 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 			orig_conninfo_needed = false;
 	}
 
-	heap_freetuple(tup);
-
-	/* Lock the subscription so nobody else can do anything with it. */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
-
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * DROP or ALTER may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCacheCopy1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
-
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
-
-	form = (Form_pg_subscription) GETSTRUCT(tup);
-
 	/*
 	 * Skip ACL checks on the subscription's foreign server, if any. If
 	 * changing the server (or replacing it with a raw connection), then the
@@ -2570,11 +2596,6 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subid = form->oid;
 
-	/* must be owner */
-	if (!object_ownercheck(SubscriptionRelationId, subid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
-					   stmt->subname);
-
 	/* DROP hook for the subscription being removed */
 	InvokeObjectDropHook(SubscriptionRelationId, subid, 0);
 
@@ -2583,20 +2604,68 @@ DropSubscription(DropSubscriptionStmt *stmt, bool isTopLevel)
 	/*
 	 * Lock the subscription so nobody else can do anything with it (including
 	 * the replication workers).
+	 *
+	 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+	 * name, check ownership, and lock inside a loop. If invalidation messages
+	 * arrive (indicating concurrent DDL), we retry. We keep the lock held
+	 * across retries and only release it if the name resolves to a different
+	 * OID on the next iteration.
 	 */
-	LockSharedObject(SubscriptionRelationId, subid, 0, AccessExclusiveLock);
+	{
+		Oid			oldSubId = InvalidOid;
+		bool		retry = false;
 
-	/*
-	 * Re-read the subscription tuple after acquiring the lock. A concurrent
-	 * ALTER or DROP may have committed before we acquired the lock.
-	 */
-	tup = SearchSysCache1(SUBSCRIPTIONOID, ObjectIdGetDatum(subid));
+		for (;;)
+		{
+			uint64		inval_count = SharedInvalidMessageCounter;
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("subscription \"%s\" does not exist",
-						stmt->subname)));
+			tup = SearchSysCache2(SUBSCRIPTIONNAME,
+								  ObjectIdGetDatum(MyDatabaseId),
+								  CStringGetDatum(stmt->subname));
+
+			if (!HeapTupleIsValid(tup))
+				ereport(ERROR,
+						(errcode(ERRCODE_UNDEFINED_OBJECT),
+						 errmsg("subscription \"%s\" does not exist",
+								stmt->subname)));
+
+			form = (Form_pg_subscription) GETSTRUCT(tup);
+			subid = form->oid;
+
+			if (!object_ownercheck(SubscriptionRelationId, subid,
+								   GetUserId()))
+			{
+				ReleaseSysCache(tup);
+				aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SUBSCRIPTION,
+							   stmt->subname);
+			}
+
+			/*
+			 * If upon retry we get the same OID, the invalidation messages
+			 * did not change the final answer.  So we're done.  If we got a
+			 * different OID, unlock the old one and lock the new one below.
+			 */
+			if (retry)
+			{
+				if (subid == oldSubId)
+					break;
+				UnlockSharedObject(SubscriptionRelationId, oldSubId, 0,
+								   AccessExclusiveLock);
+			}
+
+			LockSharedObject(SubscriptionRelationId, subid, 0,
+							 AccessExclusiveLock);
+
+			/* If no invalidation messages, we're done. */
+			if (inval_count == SharedInvalidMessageCounter)
+				break;
+
+			/* Something may have changed, retry. */
+			retry = true;
+			oldSubId = subid;
+			ReleaseSysCache(tup);
+		}
+	}
 
 	form = (Form_pg_subscription) GETSTRUCT(tup);
 	subowner = form->subowner;
-- 
2.34.1


--3eAVwo4vDNlHc8RC
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0004-Add-invalidation-based-retry-loop-for-AlterPublic.patch"



^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--1HOA+h/avFjxXHxm--






^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Hayato Kuroda (Fujitsu) <kuroda.hayato@fujitsu.com>
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--b+bwjVhifbzgesmw--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread

* [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication
@ 2026-07-03 14:46 Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 1528+ messages in thread

From: Bertrand Drouvot @ 2026-07-03 14:46 UTC (permalink / raw)

Apply the same RangeVarGetRelidExtended() style retry loop to
AlterPublication()'s tables/schemas branch that was added for subscriptions
in commit XXXX.

Previously, this branch resolved the publication name and checked ownership
at the top of AlterPublication(), then locked and re-read by OID. This left a
window where concurrent DDL could have modified the ownership and/or the name
resolution

Now the tables/schemas branch has its own complete retry loop: name
resolution, ownership check, and lock acquisition all inside the loop.

Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by:
Discussion: https://postgr.es/m/akZUpiDa1UfmzYxL%40bdtpg
---
 src/backend/commands/publicationcmds.c | 105 +++++++++++++++++--------
 1 file changed, 72 insertions(+), 33 deletions(-)
 100.0% src/backend/commands/

diff --git a/src/backend/commands/publicationcmds.c b/src/backend/commands/publicationcmds.c
index 440adb356ad..dfd707bc7d7 100644
--- a/src/backend/commands/publicationcmds.c
+++ b/src/backend/commands/publicationcmds.c
@@ -39,6 +39,7 @@
 #include "parser/parse_relation.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/lmgr.h"
+#include "storage/sinval.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inval.h"
@@ -1662,54 +1663,92 @@ AlterPublication(ParseState *pstate, AlterPublicationStmt *stmt)
 
 	rel = table_open(PublicationRelationId, RowExclusiveLock);
 
-	tup = SearchSysCacheCopy1(PUBLICATIONNAME,
-							  CStringGetDatum(stmt->pubname));
+	if (stmt->options)
+	{
+		tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+								  CStringGetDatum(stmt->pubname));
 
-	if (!HeapTupleIsValid(tup))
-		ereport(ERROR,
-				(errcode(ERRCODE_UNDEFINED_OBJECT),
-				 errmsg("publication \"%s\" does not exist",
-						stmt->pubname)));
+		if (!HeapTupleIsValid(tup))
+			ereport(ERROR,
+					(errcode(ERRCODE_UNDEFINED_OBJECT),
+					 errmsg("publication \"%s\" does not exist",
+							stmt->pubname)));
 
-	pubform = (Form_pg_publication) GETSTRUCT(tup);
+		pubform = (Form_pg_publication) GETSTRUCT(tup);
 
-	/* must be owner */
-	if (!object_ownercheck(PublicationRelationId, pubform->oid, GetUserId()))
-		aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
-					   stmt->pubname);
+		/* must be owner */
+		if (!object_ownercheck(PublicationRelationId, pubform->oid,
+							   GetUserId()))
+			aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+						   stmt->pubname);
 
-	if (stmt->options)
 		AlterPublicationOptions(pstate, stmt, rel, tup);
+	}
 	else
 	{
 		List	   *relations = NIL;
 		List	   *exceptrelations = NIL;
 		List	   *schemaidlist = NIL;
-		Oid			pubid = pubform->oid;
+		Oid			pubid;
 
-		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
-								   &exceptrelations, &schemaidlist);
+		/*
+		 * Lock the publication so nobody else can do anything with it.
+		 *
+		 * Like RangeVarGetRelidExtended() does for relations, we resolve the
+		 * name, check ownership, and lock inside a loop. If invalidation
+		 * messages arrive (indicating concurrent DDL), we retry. We keep the
+		 * lock held across retries and only release it if the name resolves
+		 * to a different OID on the next iteration.
+		 */
+		{
+			Oid			oldPubId = InvalidOid;
+			bool		retry = false;
 
-		CheckAlterPublication(stmt, tup, relations, schemaidlist);
+			for (;;)
+			{
+				uint64		inval_count = SharedInvalidMessageCounter;
 
-		heap_freetuple(tup);
+				tup = SearchSysCacheCopy1(PUBLICATIONNAME,
+										  CStringGetDatum(stmt->pubname));
 
-		/* Lock the publication so nobody else can do anything with it. */
-		LockDatabaseObject(PublicationRelationId, pubid, 0,
-						   AccessExclusiveLock);
+				if (!HeapTupleIsValid(tup))
+					ereport(ERROR,
+							(errcode(ERRCODE_UNDEFINED_OBJECT),
+							 errmsg("publication \"%s\" does not exist",
+									stmt->pubname)));
 
-		/*
-		 * It is possible that by the time we acquire the lock on publication,
-		 * concurrent DDL has removed it. We can test this by checking the
-		 * existence of publication. We get the tuple again to avoid the risk
-		 * of any publication option getting changed.
-		 */
-		tup = SearchSysCacheCopy1(PUBLICATIONOID, ObjectIdGetDatum(pubid));
-		if (!HeapTupleIsValid(tup))
-			ereport(ERROR,
-					errcode(ERRCODE_UNDEFINED_OBJECT),
-					errmsg("publication \"%s\" does not exist",
-						   stmt->pubname));
+				pubform = (Form_pg_publication) GETSTRUCT(tup);
+				pubid = pubform->oid;
+
+				if (!object_ownercheck(PublicationRelationId, pubid,
+									   GetUserId()))
+					aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_PUBLICATION,
+								   stmt->pubname);
+
+				if (retry)
+				{
+					if (pubid == oldPubId)
+						break;
+					UnlockDatabaseObject(PublicationRelationId, oldPubId, 0,
+										 AccessExclusiveLock);
+				}
+
+				LockDatabaseObject(PublicationRelationId, pubid, 0,
+								   AccessExclusiveLock);
+
+				if (inval_count == SharedInvalidMessageCounter)
+					break;
+
+				retry = true;
+				oldPubId = pubid;
+				heap_freetuple(tup);
+			}
+		}
+
+		ObjectsInPublicationToOids(stmt->pubobjects, pstate, &relations,
+								   &exceptrelations, &schemaidlist);
+
+		CheckAlterPublication(stmt, tup, relations, schemaidlist);
 
 		relations = list_concat(relations, exceptrelations);
 		AlterPublicationTables(stmt, tup, relations, pstate->p_sourcetext,
-- 
2.34.1


--3eAVwo4vDNlHc8RC--





^ permalink  raw  reply  [nested|flat] 1528+ messages in thread


end of thread, other threads:[~2026-07-03 14:46 UTC | newest]

Thread overview: 1528+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2019-12-20 01:05 [PATCH v28 01/11] Add a syntax to create Incrementally Maintainable Materialized Views Yugo Nagata <nagata@sraoss.co.jp>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:03 [PATCH v3 3/4] Add invalidation-based retry loop for Alter/Drop Subscription Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v5 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v4 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
2026-07-03 14:46 [PATCH v3 4/4] Add invalidation-based retry loop for AlterPublication Bertrand Drouvot <bertranddrouvot.pg@gmail.com>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox